feat: implement AtoCore Phase 0 + Phase 0.5 (foundation + PoC)
Complete implementation of the personal context engine foundation:
- FastAPI server with 5 endpoints (ingest, query, context/build, health, debug)
- SQLite database with 5 tables (documents, chunks, memories, projects, interactions)
- Heading-aware markdown chunker (800 char max, recursive splitting)
- Multilingual embeddings via sentence-transformers (EN/FR)
- ChromaDB vector store with cosine similarity retrieval
- Context builder with project boosting, dedup, and budget enforcement
- CLI scripts for batch ingestion and test prompt evaluation
- 19 unit tests passing, 79% coverage
- Validated on 482 real project files (8383 chunks, 0 errors)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-05 09:21:27 -04:00
|
|
|
"""Tests for the context builder."""
|
|
|
|
|
|
fix(P1+P2): alias-aware project state lookup + slash command corpus fallback
Two regression fixes from codex's review of the slash command
refactor commit (78d4e97). Both findings are real and now have
covered tests.
P1 — server-side alias resolution for project_state lookup
----------------------------------------------------------
The bug:
- /context/build forwarded the caller's project hint verbatim to
get_state(project_hint), which does an exact-name lookup against
the projects table (case-insensitive but no alias resolution)
- the project registry's alias matching was only used by the
client's auto-context path and the retriever's project-match
boost, never by the server's project_state lookup
- consequence: /atocore-context "... p05" would silently miss
trusted project state stored under the canonical id
"p05-interferometer", weakening project-hinted retrieval to
the point that an explicit alias hint was *worse* than no hint
The fix in src/atocore/context/builder.py:
- import get_registered_project from the projects registry
- before calling get_state(project_hint), resolve the hint
through get_registered_project; if a registry record exists,
use the canonical project_id for the state lookup
- if no registry record exists, fall back to the raw hint so a
hand-curated project_state entry that predates the registry
still works (backwards compat with pre-registry deployments)
The retriever already does its own alias expansion via
get_registered_project for the project-match boost, so the
retriever side was never broken — only the project_state lookup
in the builder. The fix is scoped to that one call site.
Tests added in tests/test_context_builder.py:
- test_alias_hint_resolves_through_registry: stands up a fresh
registry, sets state under "p05-interferometer", then verifies
build_context with project_hint="p05" finds the state, AND
with project_hint="interferometer" (the second alias) finds it
too, AND with the canonical id finds it. Covers all three
resolution paths.
- test_unknown_hint_falls_back_to_raw_lookup: empty registry,
set state under an unregistered project name, verify the
build_context call with that name as the hint still finds the
state. Locks in the backwards-compat behavior.
P2 — slash command no-hint fallback to corpus-wide context build
----------------------------------------------------------------
The bug:
- the slash command's no-hint path called auto-context, which
returns {"status": "no_project_match"} when project detection
fails and does NOT fall back to a plain context-build
- the slash command's own help text told the user "call without
a hint to use the corpus-wide context build" — which was a lie
because the wrapper no longer did that
- consequence: generic prompts like "what changed in AtoCore
backup policy?" or any cross-project question got a useless
no_project_match envelope instead of a context pack
The fix in .claude/commands/atocore-context.md:
- the no-hint path now does the 2-step fallback dance:
1. try `auto-context "<prompt>"` for project detection
2. if the response contains "no_project_match", fall back to
`context-build "<prompt>"` (no project arg)
- both branches return a real context pack, fail-open envelope
is preserved for genuine network errors
- the underlying client surface is unchanged (no new flags, no
new subcommands) — the fallback is per-frontend logic in the
slash command, leaving auto-context's existing semantics
intact for OpenClaw and any other caller that depends on the
no_project_match envelope as a "do nothing" signal
While I was here, also tightened the slash command's argument
parsing to delegate alias-knowledge to the registry instead of
embedding a hardcoded list:
- old version had a literal list of "atocore", "p04", "p05",
"p06" and their aliases that needed manual maintenance every
time a project was added
- new version takes the last token of $ARGUMENTS and asks the
client's `detect-project` subcommand whether it's a known
alias; if matched, it's the explicit hint, if not it's part
of the prompt
- this delegates registry knowledge to the registry, where it
belongs
Unrelated improvement noted but NOT fixed in this commit:
- _rank_chunks in builder.py also has a naive substring boost
that uses the original hint without alias expansion. The
retriever already does the right thing, so this secondary
boost is redundant. Tracked as a future cleanup but not in
scope for the P1/P2 fix; codex's findings are about
project_state lookup, not about the secondary chunk boost.
Full suite: 162 passing (was 160), 1 warning. The +2 is the two
new P1 regression tests.
2026-04-07 07:47:03 -04:00
|
|
|
import json
|
|
|
|
|
|
|
|
|
|
import atocore.config as config
|
feat: implement AtoCore Phase 0 + Phase 0.5 (foundation + PoC)
Complete implementation of the personal context engine foundation:
- FastAPI server with 5 endpoints (ingest, query, context/build, health, debug)
- SQLite database with 5 tables (documents, chunks, memories, projects, interactions)
- Heading-aware markdown chunker (800 char max, recursive splitting)
- Multilingual embeddings via sentence-transformers (EN/FR)
- ChromaDB vector store with cosine similarity retrieval
- Context builder with project boosting, dedup, and budget enforcement
- CLI scripts for batch ingestion and test prompt evaluation
- 19 unit tests passing, 79% coverage
- Validated on 482 real project files (8383 chunks, 0 errors)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-05 09:21:27 -04:00
|
|
|
from atocore.context.builder import build_context, get_last_context_pack
|
2026-04-05 09:41:59 -04:00
|
|
|
from atocore.context.project_state import init_project_state_schema, set_state
|
feat: implement AtoCore Phase 0 + Phase 0.5 (foundation + PoC)
Complete implementation of the personal context engine foundation:
- FastAPI server with 5 endpoints (ingest, query, context/build, health, debug)
- SQLite database with 5 tables (documents, chunks, memories, projects, interactions)
- Heading-aware markdown chunker (800 char max, recursive splitting)
- Multilingual embeddings via sentence-transformers (EN/FR)
- ChromaDB vector store with cosine similarity retrieval
- Context builder with project boosting, dedup, and budget enforcement
- CLI scripts for batch ingestion and test prompt evaluation
- 19 unit tests passing, 79% coverage
- Validated on 482 real project files (8383 chunks, 0 errors)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-05 09:21:27 -04:00
|
|
|
from atocore.ingestion.pipeline import ingest_file
|
|
|
|
|
from atocore.models.database import init_db
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_build_context_returns_pack(tmp_data_dir, sample_markdown):
|
|
|
|
|
"""Test that context builder returns a valid pack."""
|
|
|
|
|
init_db()
|
2026-04-05 09:41:59 -04:00
|
|
|
init_project_state_schema()
|
feat: implement AtoCore Phase 0 + Phase 0.5 (foundation + PoC)
Complete implementation of the personal context engine foundation:
- FastAPI server with 5 endpoints (ingest, query, context/build, health, debug)
- SQLite database with 5 tables (documents, chunks, memories, projects, interactions)
- Heading-aware markdown chunker (800 char max, recursive splitting)
- Multilingual embeddings via sentence-transformers (EN/FR)
- ChromaDB vector store with cosine similarity retrieval
- Context builder with project boosting, dedup, and budget enforcement
- CLI scripts for batch ingestion and test prompt evaluation
- 19 unit tests passing, 79% coverage
- Validated on 482 real project files (8383 chunks, 0 errors)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-05 09:21:27 -04:00
|
|
|
ingest_file(sample_markdown)
|
|
|
|
|
|
|
|
|
|
pack = build_context("What is AtoCore?")
|
|
|
|
|
assert pack.total_chars > 0
|
|
|
|
|
assert len(pack.chunks_used) > 0
|
|
|
|
|
assert pack.budget_remaining >= 0
|
|
|
|
|
assert "--- End Context ---" in pack.formatted_context
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_context_respects_budget(tmp_data_dir, sample_markdown):
|
|
|
|
|
"""Test that context builder respects character budget."""
|
|
|
|
|
init_db()
|
2026-04-05 09:41:59 -04:00
|
|
|
init_project_state_schema()
|
feat: implement AtoCore Phase 0 + Phase 0.5 (foundation + PoC)
Complete implementation of the personal context engine foundation:
- FastAPI server with 5 endpoints (ingest, query, context/build, health, debug)
- SQLite database with 5 tables (documents, chunks, memories, projects, interactions)
- Heading-aware markdown chunker (800 char max, recursive splitting)
- Multilingual embeddings via sentence-transformers (EN/FR)
- ChromaDB vector store with cosine similarity retrieval
- Context builder with project boosting, dedup, and budget enforcement
- CLI scripts for batch ingestion and test prompt evaluation
- 19 unit tests passing, 79% coverage
- Validated on 482 real project files (8383 chunks, 0 errors)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-05 09:21:27 -04:00
|
|
|
ingest_file(sample_markdown)
|
|
|
|
|
|
|
|
|
|
pack = build_context("What is AtoCore?", budget=500)
|
|
|
|
|
assert pack.total_chars <= 500
|
2026-04-05 17:53:23 -04:00
|
|
|
assert len(pack.formatted_context) <= 500
|
feat: implement AtoCore Phase 0 + Phase 0.5 (foundation + PoC)
Complete implementation of the personal context engine foundation:
- FastAPI server with 5 endpoints (ingest, query, context/build, health, debug)
- SQLite database with 5 tables (documents, chunks, memories, projects, interactions)
- Heading-aware markdown chunker (800 char max, recursive splitting)
- Multilingual embeddings via sentence-transformers (EN/FR)
- ChromaDB vector store with cosine similarity retrieval
- Context builder with project boosting, dedup, and budget enforcement
- CLI scripts for batch ingestion and test prompt evaluation
- 19 unit tests passing, 79% coverage
- Validated on 482 real project files (8383 chunks, 0 errors)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-05 09:21:27 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_context_with_project_hint(tmp_data_dir, sample_markdown):
|
|
|
|
|
"""Test that project hint boosts relevant chunks."""
|
|
|
|
|
init_db()
|
2026-04-05 09:41:59 -04:00
|
|
|
init_project_state_schema()
|
feat: implement AtoCore Phase 0 + Phase 0.5 (foundation + PoC)
Complete implementation of the personal context engine foundation:
- FastAPI server with 5 endpoints (ingest, query, context/build, health, debug)
- SQLite database with 5 tables (documents, chunks, memories, projects, interactions)
- Heading-aware markdown chunker (800 char max, recursive splitting)
- Multilingual embeddings via sentence-transformers (EN/FR)
- ChromaDB vector store with cosine similarity retrieval
- Context builder with project boosting, dedup, and budget enforcement
- CLI scripts for batch ingestion and test prompt evaluation
- 19 unit tests passing, 79% coverage
- Validated on 482 real project files (8383 chunks, 0 errors)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-05 09:21:27 -04:00
|
|
|
ingest_file(sample_markdown)
|
|
|
|
|
|
|
|
|
|
pack = build_context("What is the architecture?", project_hint="atocore")
|
|
|
|
|
assert len(pack.chunks_used) > 0
|
|
|
|
|
assert pack.total_chars > 0
|
|
|
|
|
|
|
|
|
|
|
fix: pass project_hint into retrieve and add path-signal ranking
Two changes that belong together:
1. builder.build_context() now passes project_hint into retrieve(),
so the project-aware boost actually fires for the retrieval pipeline
driven by /context/build. Before this, only direct /query callers
benefited from the registered-project boost.
2. retriever now applies two more ranking signals on every chunk:
- _query_match_boost: boosts chunks whose source/title/heading
echo high-signal query tokens (stop list filters out generic
words like "the", "project", "system")
- _path_signal_boost: down-weights archival noise (_archive,
_history, pre-cleanup, reviews) by 0.72 and up-weights current
high-signal docs (status, decision, requirements, charter,
system-map, error-budget, ...) by 1.18
Tests:
- test_context_builder_passes_project_hint_to_retrieval verifies
the wiring fix
- test_retrieve_downranks_archive_noise_and_prefers_high_signal_paths
verifies the new ranking helpers prefer current docs over archive
This addresses the cross-project competition and archive bleed
called out in current-state.md after the Wave 1 ingestion.
2026-04-06 18:37:07 -04:00
|
|
|
def test_context_builder_passes_project_hint_to_retrieval(monkeypatch):
|
|
|
|
|
init_db()
|
|
|
|
|
init_project_state_schema()
|
|
|
|
|
|
|
|
|
|
calls = []
|
|
|
|
|
|
|
|
|
|
def fake_retrieve(query, top_k=None, filter_tags=None, project_hint=None):
|
|
|
|
|
calls.append((query, project_hint))
|
|
|
|
|
return []
|
|
|
|
|
|
|
|
|
|
monkeypatch.setattr("atocore.context.builder.retrieve", fake_retrieve)
|
|
|
|
|
|
|
|
|
|
build_context("architecture", project_hint="p05-interferometer", budget=300)
|
|
|
|
|
|
|
|
|
|
assert calls == [("architecture", "p05-interferometer")]
|
|
|
|
|
|
|
|
|
|
|
feat: implement AtoCore Phase 0 + Phase 0.5 (foundation + PoC)
Complete implementation of the personal context engine foundation:
- FastAPI server with 5 endpoints (ingest, query, context/build, health, debug)
- SQLite database with 5 tables (documents, chunks, memories, projects, interactions)
- Heading-aware markdown chunker (800 char max, recursive splitting)
- Multilingual embeddings via sentence-transformers (EN/FR)
- ChromaDB vector store with cosine similarity retrieval
- Context builder with project boosting, dedup, and budget enforcement
- CLI scripts for batch ingestion and test prompt evaluation
- 19 unit tests passing, 79% coverage
- Validated on 482 real project files (8383 chunks, 0 errors)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-05 09:21:27 -04:00
|
|
|
def test_last_context_pack_stored(tmp_data_dir, sample_markdown):
|
|
|
|
|
"""Test that last context pack is stored for debug."""
|
|
|
|
|
init_db()
|
2026-04-05 09:41:59 -04:00
|
|
|
init_project_state_schema()
|
feat: implement AtoCore Phase 0 + Phase 0.5 (foundation + PoC)
Complete implementation of the personal context engine foundation:
- FastAPI server with 5 endpoints (ingest, query, context/build, health, debug)
- SQLite database with 5 tables (documents, chunks, memories, projects, interactions)
- Heading-aware markdown chunker (800 char max, recursive splitting)
- Multilingual embeddings via sentence-transformers (EN/FR)
- ChromaDB vector store with cosine similarity retrieval
- Context builder with project boosting, dedup, and budget enforcement
- CLI scripts for batch ingestion and test prompt evaluation
- 19 unit tests passing, 79% coverage
- Validated on 482 real project files (8383 chunks, 0 errors)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-05 09:21:27 -04:00
|
|
|
ingest_file(sample_markdown)
|
|
|
|
|
|
|
|
|
|
build_context("test prompt")
|
|
|
|
|
last = get_last_context_pack()
|
|
|
|
|
assert last is not None
|
|
|
|
|
assert last.query == "test prompt"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_full_prompt_structure(tmp_data_dir, sample_markdown):
|
|
|
|
|
"""Test that the full prompt has correct structure."""
|
|
|
|
|
init_db()
|
2026-04-05 09:41:59 -04:00
|
|
|
init_project_state_schema()
|
feat: implement AtoCore Phase 0 + Phase 0.5 (foundation + PoC)
Complete implementation of the personal context engine foundation:
- FastAPI server with 5 endpoints (ingest, query, context/build, health, debug)
- SQLite database with 5 tables (documents, chunks, memories, projects, interactions)
- Heading-aware markdown chunker (800 char max, recursive splitting)
- Multilingual embeddings via sentence-transformers (EN/FR)
- ChromaDB vector store with cosine similarity retrieval
- Context builder with project boosting, dedup, and budget enforcement
- CLI scripts for batch ingestion and test prompt evaluation
- 19 unit tests passing, 79% coverage
- Validated on 482 real project files (8383 chunks, 0 errors)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-05 09:21:27 -04:00
|
|
|
ingest_file(sample_markdown)
|
|
|
|
|
|
|
|
|
|
pack = build_context("What are memory types?")
|
|
|
|
|
assert "knowledge base" in pack.full_prompt.lower()
|
|
|
|
|
assert "What are memory types?" in pack.full_prompt
|
2026-04-05 09:41:59 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_project_state_included_in_context(tmp_data_dir, sample_markdown):
|
|
|
|
|
"""Test that trusted project state is injected into context."""
|
|
|
|
|
init_db()
|
|
|
|
|
init_project_state_schema()
|
|
|
|
|
ingest_file(sample_markdown)
|
|
|
|
|
|
|
|
|
|
# Set some project state
|
|
|
|
|
set_state("atocore", "status", "phase", "Phase 0.5 complete")
|
|
|
|
|
set_state("atocore", "decision", "database", "SQLite for structured data")
|
|
|
|
|
|
|
|
|
|
pack = build_context("What is AtoCore?", project_hint="atocore")
|
|
|
|
|
|
|
|
|
|
# Project state should appear in context
|
|
|
|
|
assert "--- Trusted Project State ---" in pack.formatted_context
|
|
|
|
|
assert "Phase 0.5 complete" in pack.formatted_context
|
|
|
|
|
assert "SQLite for structured data" in pack.formatted_context
|
|
|
|
|
assert pack.project_state_chars > 0
|
|
|
|
|
|
|
|
|
|
|
2026-04-05 17:53:23 -04:00
|
|
|
def test_trusted_state_precedence_is_restated_in_retrieved_context(tmp_data_dir, sample_markdown):
|
|
|
|
|
"""When trusted state and retrieval coexist, the context should restate precedence explicitly."""
|
|
|
|
|
init_db()
|
|
|
|
|
init_project_state_schema()
|
|
|
|
|
ingest_file(sample_markdown)
|
|
|
|
|
|
|
|
|
|
set_state("atocore", "status", "phase", "Phase 2")
|
|
|
|
|
pack = build_context("What is AtoCore?", project_hint="atocore")
|
|
|
|
|
|
|
|
|
|
assert "If retrieved context conflicts with Trusted Project State above" in pack.formatted_context
|
|
|
|
|
|
|
|
|
|
|
2026-04-05 09:41:59 -04:00
|
|
|
def test_project_state_takes_priority_budget(tmp_data_dir, sample_markdown):
|
|
|
|
|
"""Test that project state is included even with tight budget."""
|
|
|
|
|
init_db()
|
|
|
|
|
init_project_state_schema()
|
|
|
|
|
ingest_file(sample_markdown)
|
|
|
|
|
|
|
|
|
|
set_state("atocore", "status", "phase", "Phase 1 in progress")
|
|
|
|
|
|
|
|
|
|
# Small budget — project state should still be included
|
|
|
|
|
pack = build_context("status?", project_hint="atocore", budget=500)
|
|
|
|
|
assert "Phase 1 in progress" in pack.formatted_context
|
|
|
|
|
|
|
|
|
|
|
2026-04-05 17:53:23 -04:00
|
|
|
def test_project_state_respects_total_budget(tmp_data_dir, sample_markdown):
|
|
|
|
|
"""Trusted state should still fit within the total context budget."""
|
|
|
|
|
init_db()
|
|
|
|
|
init_project_state_schema()
|
|
|
|
|
ingest_file(sample_markdown)
|
|
|
|
|
|
|
|
|
|
set_state("atocore", "status", "notes", "x" * 400)
|
|
|
|
|
set_state("atocore", "decision", "details", "y" * 400)
|
|
|
|
|
|
|
|
|
|
pack = build_context("status?", project_hint="atocore", budget=120)
|
|
|
|
|
assert pack.total_chars <= 120
|
|
|
|
|
assert pack.budget_remaining >= 0
|
|
|
|
|
assert len(pack.formatted_context) <= 120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_project_hint_matches_state_case_insensitively(tmp_data_dir, sample_markdown):
|
|
|
|
|
"""Project state lookup should not depend on exact casing."""
|
|
|
|
|
init_db()
|
|
|
|
|
init_project_state_schema()
|
|
|
|
|
ingest_file(sample_markdown)
|
|
|
|
|
|
|
|
|
|
set_state("AtoCore", "status", "phase", "Phase 2")
|
|
|
|
|
pack = build_context("status?", project_hint="atocore")
|
|
|
|
|
assert "Phase 2" in pack.formatted_context
|
|
|
|
|
|
|
|
|
|
|
2026-04-05 09:41:59 -04:00
|
|
|
def test_no_project_state_without_hint(tmp_data_dir, sample_markdown):
|
|
|
|
|
"""Test that project state is not included without project hint."""
|
|
|
|
|
init_db()
|
|
|
|
|
init_project_state_schema()
|
|
|
|
|
ingest_file(sample_markdown)
|
|
|
|
|
|
|
|
|
|
set_state("atocore", "status", "phase", "Phase 1")
|
|
|
|
|
|
|
|
|
|
pack = build_context("What is AtoCore?")
|
|
|
|
|
assert pack.project_state_chars == 0
|
|
|
|
|
assert "--- Trusted Project State ---" not in pack.formatted_context
|
fix(P1+P2): alias-aware project state lookup + slash command corpus fallback
Two regression fixes from codex's review of the slash command
refactor commit (78d4e97). Both findings are real and now have
covered tests.
P1 — server-side alias resolution for project_state lookup
----------------------------------------------------------
The bug:
- /context/build forwarded the caller's project hint verbatim to
get_state(project_hint), which does an exact-name lookup against
the projects table (case-insensitive but no alias resolution)
- the project registry's alias matching was only used by the
client's auto-context path and the retriever's project-match
boost, never by the server's project_state lookup
- consequence: /atocore-context "... p05" would silently miss
trusted project state stored under the canonical id
"p05-interferometer", weakening project-hinted retrieval to
the point that an explicit alias hint was *worse* than no hint
The fix in src/atocore/context/builder.py:
- import get_registered_project from the projects registry
- before calling get_state(project_hint), resolve the hint
through get_registered_project; if a registry record exists,
use the canonical project_id for the state lookup
- if no registry record exists, fall back to the raw hint so a
hand-curated project_state entry that predates the registry
still works (backwards compat with pre-registry deployments)
The retriever already does its own alias expansion via
get_registered_project for the project-match boost, so the
retriever side was never broken — only the project_state lookup
in the builder. The fix is scoped to that one call site.
Tests added in tests/test_context_builder.py:
- test_alias_hint_resolves_through_registry: stands up a fresh
registry, sets state under "p05-interferometer", then verifies
build_context with project_hint="p05" finds the state, AND
with project_hint="interferometer" (the second alias) finds it
too, AND with the canonical id finds it. Covers all three
resolution paths.
- test_unknown_hint_falls_back_to_raw_lookup: empty registry,
set state under an unregistered project name, verify the
build_context call with that name as the hint still finds the
state. Locks in the backwards-compat behavior.
P2 — slash command no-hint fallback to corpus-wide context build
----------------------------------------------------------------
The bug:
- the slash command's no-hint path called auto-context, which
returns {"status": "no_project_match"} when project detection
fails and does NOT fall back to a plain context-build
- the slash command's own help text told the user "call without
a hint to use the corpus-wide context build" — which was a lie
because the wrapper no longer did that
- consequence: generic prompts like "what changed in AtoCore
backup policy?" or any cross-project question got a useless
no_project_match envelope instead of a context pack
The fix in .claude/commands/atocore-context.md:
- the no-hint path now does the 2-step fallback dance:
1. try `auto-context "<prompt>"` for project detection
2. if the response contains "no_project_match", fall back to
`context-build "<prompt>"` (no project arg)
- both branches return a real context pack, fail-open envelope
is preserved for genuine network errors
- the underlying client surface is unchanged (no new flags, no
new subcommands) — the fallback is per-frontend logic in the
slash command, leaving auto-context's existing semantics
intact for OpenClaw and any other caller that depends on the
no_project_match envelope as a "do nothing" signal
While I was here, also tightened the slash command's argument
parsing to delegate alias-knowledge to the registry instead of
embedding a hardcoded list:
- old version had a literal list of "atocore", "p04", "p05",
"p06" and their aliases that needed manual maintenance every
time a project was added
- new version takes the last token of $ARGUMENTS and asks the
client's `detect-project` subcommand whether it's a known
alias; if matched, it's the explicit hint, if not it's part
of the prompt
- this delegates registry knowledge to the registry, where it
belongs
Unrelated improvement noted but NOT fixed in this commit:
- _rank_chunks in builder.py also has a naive substring boost
that uses the original hint without alias expansion. The
retriever already does the right thing, so this secondary
boost is redundant. Tracked as a future cleanup but not in
scope for the P1/P2 fix; codex's findings are about
project_state lookup, not about the secondary chunk boost.
Full suite: 162 passing (was 160), 1 warning. The +2 is the two
new P1 regression tests.
2026-04-07 07:47:03 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_alias_hint_resolves_through_registry(tmp_data_dir, sample_markdown, monkeypatch):
|
|
|
|
|
"""An alias hint like 'p05' should find project state stored under 'p05-interferometer'.
|
|
|
|
|
|
|
|
|
|
This is the regression test for the P1 finding from codex's review:
|
|
|
|
|
/context/build was previously doing an exact-name lookup that
|
|
|
|
|
silently dropped trusted project state when the caller passed an
|
|
|
|
|
alias instead of the canonical project id.
|
|
|
|
|
"""
|
|
|
|
|
init_db()
|
|
|
|
|
init_project_state_schema()
|
|
|
|
|
ingest_file(sample_markdown)
|
|
|
|
|
|
|
|
|
|
# Stand up a minimal project registry that knows the aliases.
|
|
|
|
|
# The registry lives in a JSON file pointed to by
|
|
|
|
|
# ATOCORE_PROJECT_REGISTRY_PATH; the dataclass-driven loader picks
|
|
|
|
|
# it up on every call (no in-process cache to invalidate).
|
|
|
|
|
registry_path = tmp_data_dir / "project-registry.json"
|
|
|
|
|
registry_path.write_text(
|
|
|
|
|
json.dumps(
|
|
|
|
|
{
|
|
|
|
|
"projects": [
|
|
|
|
|
{
|
|
|
|
|
"id": "p05-interferometer",
|
|
|
|
|
"aliases": ["p05", "interferometer"],
|
|
|
|
|
"description": "P05 alias-resolution regression test",
|
|
|
|
|
"ingest_roots": [
|
|
|
|
|
{"source": "vault", "subpath": "incoming/projects/p05"}
|
|
|
|
|
],
|
|
|
|
|
}
|
|
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
),
|
|
|
|
|
encoding="utf-8",
|
|
|
|
|
)
|
|
|
|
|
monkeypatch.setenv("ATOCORE_PROJECT_REGISTRY_PATH", str(registry_path))
|
|
|
|
|
config.settings = config.Settings()
|
|
|
|
|
|
|
|
|
|
# Trusted state is stored under the canonical id (the way the
|
|
|
|
|
# /project/state endpoint always writes it).
|
|
|
|
|
set_state(
|
|
|
|
|
"p05-interferometer",
|
|
|
|
|
"status",
|
|
|
|
|
"next_focus",
|
|
|
|
|
"Wave 2 trusted-operational ingestion",
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# The bug: pack with alias hint used to silently miss the state.
|
|
|
|
|
pack_with_alias = build_context("status?", project_hint="p05", budget=2000)
|
|
|
|
|
assert "Wave 2 trusted-operational ingestion" in pack_with_alias.formatted_context
|
|
|
|
|
assert pack_with_alias.project_state_chars > 0
|
|
|
|
|
|
|
|
|
|
# The canonical id should still work the same way.
|
|
|
|
|
pack_with_canonical = build_context(
|
|
|
|
|
"status?", project_hint="p05-interferometer", budget=2000
|
|
|
|
|
)
|
|
|
|
|
assert "Wave 2 trusted-operational ingestion" in pack_with_canonical.formatted_context
|
|
|
|
|
|
|
|
|
|
# A second alias should also resolve.
|
|
|
|
|
pack_with_other_alias = build_context(
|
|
|
|
|
"status?", project_hint="interferometer", budget=2000
|
|
|
|
|
)
|
|
|
|
|
assert "Wave 2 trusted-operational ingestion" in pack_with_other_alias.formatted_context
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_unknown_hint_falls_back_to_raw_lookup(tmp_data_dir, sample_markdown, monkeypatch):
|
|
|
|
|
"""A hint that isn't in the registry should still try the raw name.
|
|
|
|
|
|
|
|
|
|
This preserves backwards compatibility with hand-curated
|
|
|
|
|
project_state entries that predate the project registry.
|
|
|
|
|
"""
|
|
|
|
|
init_db()
|
|
|
|
|
init_project_state_schema()
|
|
|
|
|
ingest_file(sample_markdown)
|
|
|
|
|
|
|
|
|
|
# Empty registry — the hint won't resolve through it.
|
|
|
|
|
registry_path = tmp_data_dir / "project-registry.json"
|
|
|
|
|
registry_path.write_text('{"projects": []}', encoding="utf-8")
|
|
|
|
|
monkeypatch.setenv("ATOCORE_PROJECT_REGISTRY_PATH", str(registry_path))
|
|
|
|
|
config.settings = config.Settings()
|
|
|
|
|
|
|
|
|
|
set_state("orphan-project", "status", "phase", "Solo run")
|
|
|
|
|
|
|
|
|
|
pack = build_context("status?", project_hint="orphan-project", budget=2000)
|
|
|
|
|
assert "Solo run" in pack.formatted_context
|
2026-04-11 11:35:40 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_project_memories_included_in_pack(tmp_data_dir, sample_markdown):
|
|
|
|
|
"""Active project-scoped memories for the target project should
|
|
|
|
|
land in a dedicated '--- Project Memories ---' band so the
|
|
|
|
|
Phase 9 reflection loop has a retrieval outlet."""
|
|
|
|
|
from atocore.memory.service import create_memory
|
|
|
|
|
|
|
|
|
|
init_db()
|
|
|
|
|
init_project_state_schema()
|
|
|
|
|
ingest_file(sample_markdown)
|
|
|
|
|
|
|
|
|
|
mem = create_memory(
|
|
|
|
|
memory_type="project",
|
|
|
|
|
content="the mirror architecture is Option B conical back for p04-gigabit",
|
|
|
|
|
project="p04-gigabit",
|
|
|
|
|
confidence=0.9,
|
|
|
|
|
)
|
|
|
|
|
# A sibling memory for a different project must NOT leak into the pack.
|
|
|
|
|
create_memory(
|
|
|
|
|
memory_type="project",
|
|
|
|
|
content="polisher suite splits into sim, post, control, contracts",
|
|
|
|
|
project="p06-polisher",
|
|
|
|
|
confidence=0.9,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
pack = build_context(
|
|
|
|
|
"remind me about the mirror architecture",
|
|
|
|
|
project_hint="p04-gigabit",
|
|
|
|
|
budget=3000,
|
|
|
|
|
)
|
|
|
|
|
assert "--- Project Memories ---" in pack.formatted_context
|
|
|
|
|
assert "Option B conical back" in pack.formatted_context
|
|
|
|
|
assert "polisher suite splits" not in pack.formatted_context
|
|
|
|
|
assert pack.project_memory_chars > 0
|
|
|
|
|
assert mem.project == "p04-gigabit"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_project_memories_absent_without_project_hint(tmp_data_dir, sample_markdown):
|
|
|
|
|
"""Without a project hint, project memories stay out of the pack —
|
|
|
|
|
cross-project bleed would rot the signal."""
|
|
|
|
|
from atocore.memory.service import create_memory
|
|
|
|
|
|
|
|
|
|
init_db()
|
|
|
|
|
init_project_state_schema()
|
|
|
|
|
ingest_file(sample_markdown)
|
|
|
|
|
|
|
|
|
|
create_memory(
|
|
|
|
|
memory_type="project",
|
|
|
|
|
content="scoped project knowledge that should not leak globally",
|
|
|
|
|
project="p04-gigabit",
|
|
|
|
|
confidence=0.9,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
pack = build_context("tell me something", budget=3000)
|
|
|
|
|
assert "--- Project Memories ---" not in pack.formatted_context
|
|
|
|
|
assert pack.project_memory_chars == 0
|
2026-04-11 12:47:05 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_project_memories_query_relevance_ordering(tmp_data_dir, sample_markdown):
|
|
|
|
|
"""When the budget only fits one memory, query-relevance ordering
|
|
|
|
|
should pick the one the query is actually about — even if another
|
|
|
|
|
memory has higher confidence.
|
|
|
|
|
|
|
|
|
|
Regression for the 2026-04-11 p05-vendor-signal harness failure:
|
|
|
|
|
memory selection was fixed-order by confidence, so a lower-ranked
|
|
|
|
|
vendor memory got starved out of the budget when a query was
|
|
|
|
|
specifically about vendors.
|
|
|
|
|
"""
|
|
|
|
|
from atocore.memory.service import create_memory
|
|
|
|
|
|
|
|
|
|
init_db()
|
|
|
|
|
init_project_state_schema()
|
|
|
|
|
ingest_file(sample_markdown)
|
|
|
|
|
|
|
|
|
|
create_memory(
|
|
|
|
|
memory_type="project",
|
|
|
|
|
content="the folded-beam interferometer uses a CGH stage and fold mirror",
|
|
|
|
|
project="p05-interferometer",
|
|
|
|
|
confidence=0.97,
|
|
|
|
|
)
|
|
|
|
|
create_memory(
|
|
|
|
|
memory_type="knowledge",
|
|
|
|
|
content="vendor signal: Zygo Verifire SV is the strongest value path for the interferometer",
|
|
|
|
|
project="p05-interferometer",
|
|
|
|
|
confidence=0.85,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
pack = build_context(
|
|
|
|
|
"what is the current vendor signal for the interferometer",
|
|
|
|
|
project_hint="p05-interferometer",
|
|
|
|
|
budget=1200, # tight enough that only one project memory fits
|
|
|
|
|
)
|
|
|
|
|
assert "Zygo Verifire SV" in pack.formatted_context
|
|
|
|
|
assert pack.project_memory_chars > 0
|